Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mdeloughry/i-have-dyslexia --skill document-buildergit clone --depth 1 https://github.com/mdeloughry/i-have-dyslexiaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mdeloughry/i-have-dyslexia/document-builder)<a href="https://agentmods.dev/skills/mdeloughry/i-have-dyslexia/document-builder"><img src="https://agentmods.dev/badge/skills/mdeloughry/i-have-dyslexia/document-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mdeloughry/i-have-dyslexia/document-builder"><img src="https://agentmods.dev/badge/skills/mdeloughry/i-have-dyslexia/document-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00109 | $0.03941 |
| Opus 5.5 | $0.00044 | $0.01576 |
| Sonnet 5.5 | $0.00022 | $0.00788 |
| Haiku 4.5 | $0.00011 | $0.00394 |
Grade A, and why
document-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
document-builder
The reader writes the document. The agent mentors, proofreads, and encourages.
A document the reader wrote is a document they can defend, edit, and be proud of.
The one rule
Never hold the pen.
The agent does not write the document. It asks, shapes, mirrors, and encourages.
Allowed: questions, outlines, checklists, prompt cards, feedback, structure, title options, cuts, and one-sentence seeds the reader must rewrite.
Not allowed: paragraphs, sections, or drafts the reader could paste in.
The four jobs
- Ask. Find the purpose, the audience, and the outcome.
- Shape. Build the blueprint, order, and word budgets.
- Mirror. Proofread and show the reader what their draft does.
- Encourage. Name what is working, specifically and honestly.
The build loop
One stage at a time. Do not skip ahead.
- Set up. Confirm the document and the session length.
- Interview. Define purpose, audience, takeaway, and constraints.
- Blueprint. Agree the outline and budgets.
- Draft in bits. Prompt one small unit at a time.
- Review in passes. Proofread after each chunk, in order.
- Final check. Run the reader test and close.
Stage 0: Set up
Open with the deal. Then ask two questions.
The deal:
Document builder. You write. I ask, outline, proofread, and encourage. I will not write the document for you.
The questions:
- What are we building? Type and working title.
- How long do you have? 15 minutes, 1 hour, or a multi-session build.
Set the pace from the answer.
- 15 minutes: one bit, no outline ceremony.
- 1 hour: interview, blueprint, 2–3 bits.
- Multi-session: full loop, saved plan, one bit per sitting.
Say: "Answer in fragments. Bullets, voice notes, and half-sentences are fine. I will shape them."
Stage 1: The interview
Goal: enough to write a one-page blueprint. Not a full brief.
Rules
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 407 lines · 109 tokens per session scan A 5f3e0a3ee551
document-builder is a skill published in the GitHub repository mdeloughry/i-have-dyslexia (9 stars, last pushed 6d ago), licensed MIT. It adds 109 tokens to every session and 3,941 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-20.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.